# Research, Safety at Thinking Machines

- Company: Thinking Machines
- What the company does: Connectionism: Research Blog by Thinking Machines Lab. Backed by a16z, Accel and GV.
- Company website: https://thinkingmachines.ai/
- Type: Startups (AI role)
- Level: Mid level
- Location: San Francisco
- Work setup: Remote
- Pay: $350K to $475K base salary per year (USD)
- Posted: 2026-08-24
- Apply by: 2026-10-08
- Apply: https://jobs.ashbyhq.com/thinkingmachines/01aba71c-b55f-4df5-b803-dc545e6a9434
- Page: https://www.1752.vc/careers/jobs/thinking-machines-research-safety/

## About the role

As a safety researcher, you'll work toward ensuring our models are safe and trustworthy. The role sits at the intersection of research and hands-on technical work. A central question is how models come to handle harmful or dual-use requests: what they learn from data, how training shapes where they refuse and where they engage, and what makes those boundaries reliable. You'll explore the science behind these behaviors and design experiments that inform how our models are trained and evaluated.

## What they're looking for

- Bachelor’s degree or equivalent experience in Computer Science, Machine Learning, Physics, Mathematics, or a related discipline with strong theoretical and empirical grounding
- Background in AI safety research, with hands-on experience in at least one area of safety, such as: RLHF/RLAIF, alignment and preference modeling, deliberative alignment, safety evaluations, or red-teaming
- Proficiency in Python and familiarity with deep learning frameworks (e.g., PyTorch, TensorFlow, or JAX). Comfort debugging distributed training and writing code that scales
- Clarity in communication, an ability to explain complex technical concepts in writing
- Preferred qualifications — we encourage you to apply if you meet some but not all of these:
- Experience building evaluations for long-horizon, multi-step, or agentic tasks

Tags: Research